13 papers
Defense Against LLM Backdoors using Critical Neuron Isolation Pruning
Yuxi Li, Zhibo Zhang, Kailong Wang +3
Large language models (LLMs) are vulnerable to backdoor attacks, where hidden triggers induce malicious outputs. Existing defenses generally fall into inference-time detection or t…
SwitchPatch: Physical Adversarial Attack Strategy with Switchable Adversarial Objectives
Hanrui Jiang, Yutong Wu, Shiyi Yao +5
Physical adversarial patch (PAP) attacks attach carefully crafted patches to physical objects to manipulate a deployed model. However, existing PAP attacks suffer from several limi…
When Search Goes Wrong: Red-Teaming Web-Augmented Large Language Models
Haoran Ou, Kangjie Chen, Xingshuo Han +4
Large Language Models (LLMs) have been augmented with web search to overcome the limitations of the static knowledge boundary by accessing up-to-date information from the open Inte…
Beyond Retrieval: Improving Evidence Quality for LLM-based Multimodal Fact-Checking
Haoran Ou, Gelei Deng, Xingshuo Han +4
The increasing multimodal disinformation, where deceptive claims are reinforced through coordinated text and visual content, poses significant challenges to automated fact-checking…
The Fluorescent Veil: A Stealthy and Effective Physical Adversarial Patch Against Traffic Sign Recognition
Shuai Yuan, Xingshuo Han, Hongwei Li +5
Recently, traffic sign recognition (TSR) systems have become a prominent target for physical adversarial attacks. These attacks typically rely on conspicuous stickers and projectio…
Work Zones challenge VLM Trajectory Planning: Toward Mitigation and Robust Autonomous Driving
Yifan Liao, Zhen Sun, Xiaoyun Qiu +7
Visual Language Models (VLMs), with powerful multimodal reasoning capabilities, are gradually integrated into autonomous driving by several automobile manufacturers to enhance plan…